Skip to content

mf-caglar/cert-nexus-certified-data-scientist

Repository files navigation

CertNexus Certified Data Scientist Project

  • This project was completed as part of the CertNexus Data Science Practitioner professional certificate program on Coursera. It was not the same as the one in the course. There are some additional codes to obtain a better dataset and models. Indeed, the project here is not complete since the model has overfitting and need some further validations but it will take so much more time and effort and I've already got bored and overwhelmed I simply passed it. Let us make it happen in the next project! 💪🤩
  • See the data, plots, notebooks and the pickles of models in related folders. There are also presentations in pdf and pptx formats.

Project Overview

The primary objective of this project was to analyze and process data stored in the company database. We developed three machine learning models to address key business challenges:

  • Customer Churn Prediction: Predicting which customers are likely to churn.
  • Customer Spending Prediction: Forecasting customer spending patterns.
  • Customer Segmentation: Creating segments of customers for targeted business strategies.

Key Learnings

  • Coding Proficiency: While coding is vital, mastering the underlying concepts significantly simplifies the implementation process.
  • Tool Usage: While tools like ChatGPT and Gemini can expedite certain tasks, they should complement rather than replace creative thinking and exploration. Relying solely on automation can limit our exposure to diverse perspectives and innovative solutions.
  • Importance of Mathematical Foundation: This project underscored for me the crucial role of mathematics in machine learning. Concepts such as statistics and linear algebra is forming the backbone of data science projects for real. Now it's time for new dirty data and crazy math!

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published